In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in physically implausible artifacts such as interpenetration and object floating. To overcome these issues, we introduce a physics-guided reconstruction framework. We begin with a kinematic estimate and then refine it by training a policy with reinforcement learning (RL). This policy is optimized to reproduce the interaction in a physics simulator. Because kinematic estimates are typically noisy, naive RL training can fail. Therefore, we propose an adaptive sampling strategy with a dual self-updating mechanism that can identify the frames with the most informative and reliable kinematic reconstruction. Our process progressively improves reconstruction quality and yields physically consistent HOI sequences. We demonstrate our approach on two standard HOI benchmarks and achieve clear improvements in physical plausibility metrics over state-of-the-art methods. Project Page: https://dingbang777.github.io/RePHO/
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
Stanford University（斯坦福大学）；University of Southern California（南加州大学）；Bosch Research North America（博世北美研究院）；Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心（BCAI））
University of Oulu（奥卢大学）；Czech Technical University（捷克理工大学）；Tampere University（坦佩雷大学）
Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations. In recent works, those priors have been learned in an end-to-end manner from large datasets by using deep neural networks. In this paper, we propose guiding depth estimation to favor planar structures that are ubiquitous especially in indoor environments. This is achieved by incorporating a non-local coplanarity constraint to the network with a novel attention mechanism called depth-attention volume (DAV…
Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining
Beijing Institute of Technology（北京理工大学）；State Key Laboratory of General Artificial Intelligence, BIGAI（国家一般人工智能重点实验室，BIGAI）；Deep Glint；Zhejiang University（浙江大学）；The University of Hong Kong（香港大学）；Shandong Agricultural University（山东农业大学）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Facebook Reality Labs（Facebook现实实验室）
Marker-less 3D human motion capture from a single colour camera has seen significant progress. However, it is a very challenging and severely ill-posed problem. In consequence, even the most accurate state-of-the-art approaches have significant limitations. Purely kinematic formulations on the basis of individual joints or skeletons, and the frequent frame-wise reconstruction in state-of-the-art methods greatly limit 3D accuracy and temporal stability compared to multi-view or marker-based motion capture. Further, captured 3D poses are often physically incorrect and biomechanically implausible…
We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and differentiable functions for modeling the time-varying structure and the appearance of the scene. We jointly train a time-invariant static NeRF and a time-varying dynamic NeRF, and learn how to blend the results in an unsupervised manner. However, learning this implicit function from a single video is highly ill-posed (with infinitely many solutions that match…
Universidade Federal de Minas Gerais (UFMG)（米纳斯吉拉斯联邦大学）；INRIA（法国国家信息与自动化研究所）
Creating plausible virtual actors from images of real actors remains one of the key challenges in computer vision and computer graphics. Marker-less human motion estimation and shape modeling from images in the wild bring this challenge to the fore. Although the recent advances on view synthesis and image-to-image translation, currently available formulations are limited to transfer solely style and do not take into account the character's motion and shape, which are by nature intermingled to produce plausible human forms. In this paper, we propose a unifying formulation for transferring appea…
ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning
Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）；Harbin Institute of Technology（哈尔滨工业大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
We present PHORHUM, a novel, end-to-end trainable, deep neural network methodology for photorealistic 3D human reconstruction given just a monocular RGB image. Our pixel-aligned method estimates detailed 3D geometry and, for the first time, the unshaded surface color together with the scene illumination. Observing that 3D supervision alone is not sufficient for high fidelity color reconstruction, we introduce patch-based rendering losses that enable reliable color reconstruction on visible parts of the human, and detailed and plausible color estimation for the non-visible parts. Moreover, our …
We propose an approach to estimate arm and hand dynamics from monocular video by utilizing the relationship between arm and hand. Although monocular full human motion capture technologies have made great progress in recent years, recovering accurate and plausible arm twists and hand gestures from in-the-wild videos still remains a challenge. To solve this problem, our solution is proposed based on the fact that arm poses and hand gestures are highly correlated in most real situations. To fully exploit arm-hand correlation as well as inter-frame information, we carefully design a Spatial-Tempor…
Korea Electronics Technology Institute (KETI)（韩国电子技术研究院（KETI））
We present an approach to generating 3D human models from images. The key to our framework is that we predict double-sided orthographic depth maps and color images from a single perspective projected image. Our framework consists of three networks. The first network predicts normal maps to recover geometric details such as wrinkles in the clothes and facial regions. The second network predicts shade-removed images for the front and back views by utilizing the predicted normal maps. The last multi-headed network takes both normal maps and shade-free images and predicts depth maps while selectiv…
University of Cambridge（剑桥大学）；Google Research（谷歌研究院）；Simon Fraser University（西蒙弗雷泽大学）
Given a monocular video, segmenting and decoupling dynamic objects while recovering the static environment is a widely studied problem in machine intelligence. Existing solutions usually approach this problem in the image domain, limiting their performance and understanding of the environment. We introduce Decoupled Dynamic Neural Radiance Field (D$^2$NeRF), a self-supervised approach that takes a monocular video and learns a 3D scene representation which decouples moving objects, including their shadows, from the static background. Our method represents the moving objects and the static backg…
Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetrating the ground and bodies leaning at extreme angles. In this paper, we present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input. We first estimate ground contact timings with a novel prediction network which is trained without hand-labeled data. A physics-based trajectory optimization then solves for a physically-plausible motion, based o…
Nanyang Technological University（南洋理工大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Recovering a textured 3D mesh from a monocular image is highly challenging, particularly for in-the-wild objects that lack 3D ground truths. In this work, we present MeshInversion, a novel framework to improve the reconstruction by exploiting the generative prior of a 3D GAN pre-trained for 3D textured mesh synthesis. Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation. Since the pre-trained GAN encapsulates rich 3D semantics in terms of mesh geometry and texture, searching within the GAN ma…
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Shanghai Frontiers Science Center of Human-centered Artificial Intelligence（上海人本人工智能前沿科学中心）
Monocular 3D motion capture (mocap) is beneficial to many applications. The use of a single camera, however, often fails to handle occlusions of different body parts and hence it is limited to capture relatively simple movements. We present a light-weight, hybrid mocap technique called HybridCap that augments the camera with only 4 Inertial Measurement Units (IMUs) in a learning-and-optimization framework. We first employ a weakly-supervised and hierarchical motion inference module based on cooperative Gated Recurrent Unit (GRU) blocks that serve as limb, body and root trackers as well as an i…
University of Alberta（阿尔伯塔大学）；Demant A/S（戴蒙特公司）；Canadian Forest Service, Natural Resources Canada（加拿大自然资源部加拿大林务局）
In nature, the collective behavior of animals, such as flying birds is dominated by the interactions between individuals of the same species. However, the study of such behavior among the bird species is a complex process that humans cannot perform using conventional visual observational techniques such as focal sampling in nature. For social animals such as birds, the mechanism of group formation can help ecologists understand the relationship between social cues and their visual characteristics over time (e.g., pose and shape). But, recovering the varying pose and shapes of flying birds is a…
FlowHMR: Physically Plausible Motion Capture from Video
Peking University（北京大学）；The Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）；East China Normal University（华东师范大学）；Sun Yat-sen University（中山大学）；Zhejiang University（浙江大学）
We focus on the task of estimating a physically plausible articulated human motion from monocular video. Existing approaches that do not consider physics often produce temporally inconsistent output with motion artifacts, while state-of-the-art physics-based approaches have either been shown to work only in controlled laboratory conditions or consider simplified body-ground contact limited to feet. This paper explores how these shortcomings can be addressed by directly incorporating a fully-featured physics engine into the pose estimation process. Given an uncontrolled, real-world scene as inp…
University of Chinese Academy of Sciences（中国科学院大学）
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and orientation, and then combine these estimations with perspective geometry constraints to compute position attribute. Further, we reformulate the geometric constraints as a differentiable version and embed it into the network to reduce running time while maintaining the consistency of model outputs in an end-to-end fashion. Benefiting from this simple structure, we t…
Harbin Institute of Technology（哈尔滨工业大学）；JD AI Research（京东人工智能研究院）
We describe an end-to-end method for recovering 3D human body mesh from single images and monocular videos. Different from the existing methods try to obtain all the complex 3D pose, shape, and camera parameters from one coupling feature, we propose a skeleton-disentangling based framework, which divides this task into multi-level spatial and temporal granularity in a decoupling manner. In spatial, we propose an effective and pluggable "disentangling the skeleton from the details" (DSD) module. It reduces the complexity and decouples the skeleton, which lays a good foundation for temporal mode…
We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving. Existing methods for recovering depth for dynamic, non-rigid objects from monocular video impose strong assumptions on the objects' motion and may only recover sparse depth. In this paper, we take a data-driven approach and learn human depth priors from a new source of data: thousands of Internet videos of people imitating mannequins, i.e., freezing in diverse, natural poses, while a hand-held camera tours the scene. Because people are stationary, training data c…
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；Tencent（腾讯）
We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views. Our method is based on a dynamic Neural Radiance Field (NeRF) rigged by a mesh-based parametric 3D human model serving as a geometry proxy. Previous methods usually rely on multi-view videos or accurate 3D geometry information as additional inputs; besides, most methods suffer from degraded quality when generalized to unseen poses. We identify that the key to generalization is a good input embedding for querying dynamic NeRF: A …
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Facebook AI Research（Facebook人工智能研究实验室）
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering several plausible reconstructions compatible with the input data. We suggest that ambiguities can be modelled more effectively by parametrizing the possible body shapes and poses via a suitable 3D model, such as SMPL for humans. We propose to learn a multi-hypothesis neural network regressor using a best-of-M loss, where each of the M hypotheses is constraine…
TU Braunschweig（布伦瑞克工业大学）；MPI for Informatics（马克斯·普朗克信息学研究所）
Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments…
Due to the visual ambiguity, purely kinematic formulations on monocular human motion capture are often physically incorrect, biomechanically implausible, and can not reconstruct accurate interactions. In this work, we focus on exploiting the high-precision and non-differentiable physics simulator to incorporate dynamical constraints in motion capture. Our key-idea is to use real physical supervisions to train a target pose distribution prior for sampling-based motion control to capture physically plausible human motion. To obtain accurate reference motion with terrain interactions for the samp…
Recovering 3D human mesh from monocular images is a popular topic in computer vision and has a wide range of applications. This paper aims to estimate 3D mesh of multiple body parts (e.g., body, hands) with large-scale differences from a single RGB image. Existing methods are mostly based on iterative optimization, which is very time-consuming. We propose to train a single-shot model to achieve this goal. The main challenge is lacking training data that have complete 3D annotations of all body parts in 2D images. To solve this problem, we design a multi-branch framework to disentangle the regr…
Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with Geometric and Motion Constraints
Wuhan University（武汉大学）；Hong Kong Embodied AI Lab（香港具身AI实验室）；The Chinese University of Hong Kong（香港中文大学）；Peking Union Medical College（北京协和医学院）；University of Macau（澳门大学）；Zhejiang University（浙江大学）
